Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (1): 14-16.

• 博士论坛 • Previous Articles     Next Articles

High efficient algorithm of modified Particle Swarm Optimization

LI Hong-liang1,2,HOU Chao-zhen1,ZHOU Shao-sheng2   

  1. 1.Department of Automatic Control,Beijing Institute of Technology,Beijing 100081,China
    2.Institute of Automation,Qufu Normal University,Qufu,Shandong 273165,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-01 Published:2008-01-01
  • Contact: LI Hong-liang

一种高效的改进粒子群优化算法

李洪亮1,2,侯朝桢1,周绍生2   

  1. 1.北京理工大学 自动控制系,北京 100081
    2.曲阜师范大学 自动化研究所,山东 曲阜 273165
  • 通讯作者: 李洪亮

Abstract: A high efficient algorithm of modified particle swarm optimization is presented.Population divided into subpopulations,each subpopulation has its special role and information exchanged between them.This strategy has improved the ability of local search along with the global search ability.Experiments show that this method has been significantly improved on both optimization speed and computational accuracy.

Key words: Particle Swarm Optimization(PSO), evolutionary algorithm, strategy

摘要: 提出了一种高效的改进的粒子群优化策略,把整个群体分为几个子群体,进行子群体的专业化社会分工与信息交换,该策略在提高算法局部搜索能力的同时也兼顾了全局搜索能力。测试表明,与现有方法比较,该方法全局寻优的精度与速度有明显提高。

关键词: 粒子群优化, 进化算法, 策略